Hugging Face's logo

alakxender
/
w2v-bert-2.0-dhivehi-cv

Automatic Speech Recognition
Transformers
Safetensors
Divehi
wav2vec2-bert
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
alakxender commited on
Commit
6ee417f
•
1 Parent(s): db0cb6f

Upload tokenizer

Browse files
Files changed (4) hide show
  1. added_tokens.json +4 -4
  2. special_tokens_map.json +6 -6
  3. tokenizer_config.json +47 -48
  4. vocab.json +63 -63
added_tokens.json CHANGED
@@ -1,4 +1,4 @@
1
- {
2
- "</s>": 62,
3
- "<s>": 61
4
- }
 
1
+ {
2
+ "</s>": 62,
3
+ "<s>": 61
4
+ }
special_tokens_map.json CHANGED
@@ -1,6 +1,6 @@
1
- {
2
- "bos_token": "<s>",
3
- "eos_token": "</s>",
4
- "pad_token": "[PAD]",
5
- "unk_token": "[UNK]"
6
- }
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "pad_token": "[PAD]",
5
+ "unk_token": "[UNK]"
6
+ }
tokenizer_config.json CHANGED
@@ -1,48 +1,47 @@
1
- {
2
- "added_tokens_decoder": {
3
- "59": {
4
- "content": "[UNK]",
5
- "lstrip": true,
6
- "normalized": false,
7
- "rstrip": true,
8
- "single_word": false,
9
- "special": false
10
- },
11
- "60": {
12
- "content": "[PAD]",
13
- "lstrip": true,
14
- "normalized": false,
15
- "rstrip": true,
16
- "single_word": false,
17
- "special": false
18
- },
19
- "61": {
20
- "content": "<s>",
21
- "lstrip": false,
22
- "normalized": false,
23
- "rstrip": false,
24
- "single_word": false,
25
- "special": true
26
- },
27
- "62": {
28
- "content": "</s>",
29
- "lstrip": false,
30
- "normalized": false,
31
- "rstrip": false,
32
- "single_word": false,
33
- "special": true
34
- }
35
- },
36
- "bos_token": "<s>",
37
- "clean_up_tokenization_spaces": true,
38
- "do_lower_case": false,
39
- "eos_token": "</s>",
40
- "model_max_length": 1000000000000000019884624838656,
41
- "pad_token": "[PAD]",
42
- "processor_class": "Wav2Vec2BertProcessor",
43
- "replace_word_delimiter_char": " ",
44
- "target_lang": null,
45
- "tokenizer_class": "Wav2Vec2CTCTokenizer",
46
- "unk_token": "[UNK]",
47
- "word_delimiter_token": "|"
48
- }
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "59": {
4
+ "content": "[UNK]",
5
+ "lstrip": true,
6
+ "normalized": false,
7
+ "rstrip": true,
8
+ "single_word": false,
9
+ "special": false
10
+ },
11
+ "60": {
12
+ "content": "[PAD]",
13
+ "lstrip": true,
14
+ "normalized": false,
15
+ "rstrip": true,
16
+ "single_word": false,
17
+ "special": false
18
+ },
19
+ "61": {
20
+ "content": "<s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "62": {
28
+ "content": "</s>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ }
35
+ },
36
+ "bos_token": "<s>",
37
+ "clean_up_tokenization_spaces": true,
38
+ "do_lower_case": false,
39
+ "eos_token": "</s>",
40
+ "model_max_length": 1000000000000000019884624838656,
41
+ "pad_token": "[PAD]",
42
+ "replace_word_delimiter_char": " ",
43
+ "target_lang": null,
44
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
45
+ "unk_token": "[UNK]",
46
+ "word_delimiter_token": "|"
47
+ }
 
vocab.json CHANGED
@@ -1,63 +1,63 @@
1
- {
2
- "[PAD]": 60,
3
- "[UNK]": 59,
4
- "|": 0,
5
- "،": 1,
6
- "؟": 2,
7
- "ا": 3,
8
- "ل": 4,
9
- "ه": 5,
10
- "ّ": 6,
11
- "ހ": 7,
12
- "ށ": 8,
13
- "ނ": 9,
14
- "ރ": 10,
15
- "ބ": 11,
16
- "ޅ": 12,
17
- "ކ": 13,
18
- "އ": 14,
19
- "ވ": 15,
20
- "މ": 16,
21
- "ފ": 17,
22
- "ދ": 18,
23
- "ތ": 19,
24
- "ލ": 20,
25
- "ގ": 21,
26
- "ޏ": 22,
27
- "ސ": 23,
28
- "ޑ": 24,
29
- "ޒ": 25,
30
- "ޓ": 26,
31
- "ޔ": 27,
32
- "ޕ": 28,
33
- "ޖ": 29,
34
- "ޗ": 30,
35
- "ޘ": 31,
36
- "ޙ": 32,
37
- "ޚ": 33,
38
- "ޛ": 34,
39
- "ޝ": 35,
40
- "ޞ": 36,
41
- "ޟ": 37,
42
- "ޠ": 38,
43
- "ޡ": 39,
44
- "ޢ": 40,
45
- "ޣ": 41,
46
- "ޤ": 42,
47
- "ޥ": 43,
48
- "ަ": 44,
49
- "ާ": 45,
50
- "ި": 46,
51
- "ީ": 47,
52
- "ު": 48,
53
- "ޫ": 49,
54
- "ެ": 50,
55
- "ޭ": 51,
56
- "ޮ": 52,
57
- "ޯ": 53,
58
- "ް": 54,
59
- "–": 55,
60
- "’": 56,
61
- "ﷲ": 57,
62
- "ﷺ": 58
63
- }
 
1
+ {
2
+ "[PAD]": 60,
3
+ "[UNK]": 59,
4
+ "|": 0,
5
+ "،": 1,
6
+ "؟": 2,
7
+ "ا": 3,
8
+ "ل": 4,
9
+ "ه": 5,
10
+ "ّ": 6,
11
+ "ހ": 7,
12
+ "ށ": 8,
13
+ "ނ": 9,
14
+ "ރ": 10,
15
+ "ބ": 11,
16
+ "ޅ": 12,
17
+ "ކ": 13,
18
+ "އ": 14,
19
+ "ވ": 15,
20
+ "މ": 16,
21
+ "ފ": 17,
22
+ "ދ": 18,
23
+ "ތ": 19,
24
+ "ލ": 20,
25
+ "ގ": 21,
26
+ "ޏ": 22,
27
+ "ސ": 23,
28
+ "ޑ": 24,
29
+ "ޒ": 25,
30
+ "ޓ": 26,
31
+ "ޔ": 27,
32
+ "ޕ": 28,
33
+ "ޖ": 29,
34
+ "ޗ": 30,
35
+ "ޘ": 31,
36
+ "ޙ": 32,
37
+ "ޚ": 33,
38
+ "ޛ": 34,
39
+ "ޝ": 35,
40
+ "ޞ": 36,
41
+ "ޟ": 37,
42
+ "ޠ": 38,
43
+ "ޡ": 39,
44
+ "ޢ": 40,
45
+ "ޣ": 41,
46
+ "ޤ": 42,
47
+ "ޥ": 43,
48
+ "ަ": 44,
49
+ "ާ": 45,
50
+ "ި": 46,
51
+ "ީ": 47,
52
+ "ު": 48,
53
+ "ޫ": 49,
54
+ "ެ": 50,
55
+ "ޭ": 51,
56
+ "ޮ": 52,
57
+ "ޯ": 53,
58
+ "ް": 54,
59
+ "–": 55,
60
+ "’": 56,
61
+ "ﷲ": 57,
62
+ "ﷺ": 58
63
+ }